Unsupervised Tumour Segmentation in PET using Local and Global Intensity-Fitting Active Surface and Alpha Matting

Ziming Zeng, Jue Wang, Bernie Tiddeman, Reyer Zwiggelaar

Research output: Contribution to journalArticlepeer-review

15 Citations (SciVal)
219 Downloads (Pure)

Abstract

This paper proposes an unsupervised tumour segmentation approach for PET data. The method computes the volumes of interest (VOIs) with sub-voxel precision by considering the limited image resolution and partial volume effects. First, an improved anisotropic diffusion filter is used to remove image noise. A hierarchical local and global intensity active surface modelling scheme is then applied to segment VOIs, followed by an alpha matting step to further refine the segmentation boundary. The proposed method is validated on real PET images of head-and-neck cancer patients with ground truth provided by human experts, as well as custom-designed phantom PET images with objective ground truth. Experimental results show that our method outperforms previous automatic approaches in terms of segmentation accuracy.
Original languageEnglish
Pages (from-to)1530-1544
Number of pages14
JournalComputers in Biology and Medicine
Volume43
Issue number10
Early online date06 Aug 2013
DOIs
Publication statusPublished - 01 Oct 2013

Keywords

  • Positron emission tomography
  • Tumour segmentation
  • Active surface modelling
  • Alpha matting
  • Mutual information

Fingerprint

Dive into the research topics of 'Unsupervised Tumour Segmentation in PET using Local and Global Intensity-Fitting Active Surface and Alpha Matting'. Together they form a unique fingerprint.

Cite this